© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118462
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paternal
    -0.06
     действительно
    -0.06
     অন্য
    -0.06
     pater
    -0.06
     veramente
    -0.06
     prerequisites
    -0.06
     timezone
    -0.06
     terbentuk
    -0.06
    timezone
    -0.06
     位置
    -0.06
    POSITIVE LOGITS
     escalate
    0.07
     estimating
    0.07
    project
    0.07
     sleeper
    0.06
     estimation
    0.06
    桁
    0.06
     Estimation
    0.06
     photoelectric
    0.06
     PROJECT
    0.06
     project
    0.06
    Activations Density 0.000%

    No Known Activations